Skip to content

[ICCV'23] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

License

Notifications You must be signed in to change notification settings

OSU-NLP-Group/LLM-Planner

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

Code for LLM-Planner.

Check project website for an overview and a demo.

News:

  • Jun 24: Due to an object grounding error in the simulator we are using, we revert the code into high-level plan generation only before fix is implemented.

Quickstart

python hlp_planner.py

This commands uses the KNN dataset to generate a high-level plan for an example task. Check out the code for more details.

Hardware

Tested on:

  • Mac M1
  • Ubuntu 18.04

Citation Information

@InProceedings{song2023llmplanner,
  author    = {Song, Chan Hee and Wu, Jiaman and Washington, Clayton and Sadler, Brian M. and Chao, Wei-Lun and Su, Yu},
  title     = {LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  month     = {October},
  year      = {2023},
}

Acknowledgements

We thank the authors of ALFWORLD for releasing their code.

License

  • LLM-Planner - MIT License
  • ALFWorld - MIT License

Contact

Questions or issues? File an issue or contact Luke Song

About

[ICCV'23] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages